© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 180
    Prev
    Next
    INDEX
    Explanations

    star rating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yur
    -0.08
    alars
    -0.07
    ouri
    -0.07
     alojamiento
    -0.07
    Cari
    -0.07
     agrega
    -0.07
    Conta
    -0.07
     Agenda
    -0.07
    Kas
    -0.07
    Agenda
    -0.07
    POSITIVE LOGITS
    ☆☆
    0.10
    級
    0.09
    级
    0.09
    程度
    0.08
     мало
    0.08
     {@
    0.08
    _LEVEL
    0.08
     LEVEL
    0.08
    xn
    0.08
    krut
    0.08
    Activations Density 0.002%

    No Known Activations